Diffusion Timestep Scheduling

Follow this topic Ask about this topic

Diffusion timestep scheduling studies when noise is added during training and where a sampler evaluates the denoising process at inference. Approaches include hand-designed cosine or log-SNR schedules, learned monotone splines, and optimization using numerical-error estimates, optimal control, reinforcement learning, or Bayesian search. Adaptive methods also allocate steps by input difficulty or task, and schedule sparse guidance or cached computation; they are evaluated across image, video, language, scientific, and discrete-generation settings. A central tension is whether schedules should be fixed and transferable or adapted to each model and sample, since benefits depend on the solver, denoiser, step budget, and quality measure.

Latest papers

64 papers10 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

Timestep Rescheduling in Diffusion Inversion
Jun 13, 2026Shangquan Sun, Ting Gong, Zhirui Liu +5Diffusion Model Inversion Diffusion Sampling
School of CyberScience and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen 518107, China · Tsinghua University · CUHK +2
Tracing the Oracle: Improving Diffusion Timestep Scheduling for 3D CT Reconstruction
Jun 4, 2026Yujia Wu, Zhaoqiang LiuDiffusion Sampling Few-Step Diffusion Sampling
The authors are with the School of Computer Science and Engineering, University of Electronic Science and Technology of China.
DEMON: Diffusion Engine for Musical Orchestrated Noise
May 27, 2026Ryan FosdickDiffusion Models Controllable Music Generation
Daydream
Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
May 26, 2026Junseo Bang, Dong Ju Mun, Hoigi Seo +2Diffusion Model Guidance Diffusion Timestep Scheduling
Dept. of Electrical and Computer Engineering · INMC · IPAI & AIIS
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
May 21, 2026Seo Taek Kong, Weina Wang, R. SrikantDiffusion Sampling Diffusion-Based Image Generation
ECE & CSL, University of Illinois Urbana-Champaign · Computer Science Department, Carnegie Mellon University · ECE, CSL & NCSA, University of Illinois Urbana-Champaign
Semantic Granularity Navigation in Image Editing
May 20, 2026Liangsi Lu, Minzhe Guo, Xuhang Chen +1Diffusion Model Sampling Diffusion Timestep Scheduling
Guangdong University of Technology, Guangzhou, China · Huizhou University, Huizhou, China.
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
May 15, 2026Renye Yan, Jikang Cheng, Shikun Sun +7Diffusion Model Alignment Diffusion Sampling
1Peking University · 2Tsinghua University · 3Nanjing University +1
Is Monotonic Sampling Necessary in Diffusion Models?
May 12, 2026Muhammad Haris KhanDiffusion Sampling Diffusion Timestep Scheduling
Department of Computer Science, University of Copenhagen, Denmark
Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
May 8, 2026Hanhan Zhou, Shamik Roy, Rashmi GangadharaiahLanguage Model Steering Diffusion Language Model Decoding
AWS AI Labs Santa Clara, CA 95054
NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
May 8, 2026Wen Huang, Haoran Sun, Yongjian Guo +8Action-Conditioned Video Generation Action-Conditioned World Models
Tsinghua University · Peking University · JDT AI Infra +1
Not All Tokens Need 40 Steps: Heterogeneous Step Allocation in Diffusion Transformers for Efficient Video Generation
May 7, 2026Ernie Chu, Vishal M. PatelVideo Diffusion Models Diffusion Transformer
Johns Hopkins University Baltimore, MD 21218
Information-geometric adaptive sampling for graph diffusion
Apr 30, 2026Yuhui Lu, Wenjing Liu, Kun ZhanInformation Geometry Graph Generation
School of Information Science and Engineering, Lanzhou University, Gansu, China.
Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
Apr 21, 2026Johannes Schusterbauer, Ming Gui, Yusong Li +3Diffusion Model Sampling Diffusion Sampling
Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training
Apr 9, 2026Constantin Le Cleï, Nils Thuerey, Xiaoxiang ZhuDiffusion Models Autoregressive Diffusion
Technical University of Munich, Munich, Germany.
A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
Mar 25, 2026Changyu Liu, James Chenhao Liang, Wenhao Yang +6Visual Representation Learning Diffusion Models
University of Missouri–Kansas City · U. S. Naval Research Laboratory · Lamar University +5
CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
Mar 24, 2026Shaonan Liu, Yuichiro Iwashita, Soichiro Nakako +2Synthetic Data Generation Diffusion Models
Department of Core Informatics, Graduate School of Informatics, Osaka Metropolitan University, Sakai, Osaka 599-8531, Japan · Smart Data & Knowledge Services Department, German Research Center for Artificial Intelligence (DFKI GmbH), 67663 Kaiserslautern, Germany · Department of Computer Science, RPTU University Kaiserslautern-Landau, 67663 Kaiserslautern, Germany +1
Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
Mar 22, 2026Yu-Shan Tai, An-Yeu, WuDiffusion Model Sampling Diffusion Sampling
Andy · Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan
Spectrally-Guided Diffusion Noise Schedules
Mar 19, 2026Carlos Esteves, Ameesh MakadiaDiffusion-Based Image Generation Diffusion Timestep Scheduling
Google Research.
Few-Step Diffusion Sampling Through Instance-Aware Discretizations
Mar 18, 2026Liangyu Yuan, Ruoyu Wang, Tong Zhao +4Few-Step Diffusion Sampling Diffusion Timestep Scheduling
Westlake University · Tongji University · Zhejiang University +1
Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
Mar 16, 2026Ping Chen, Xiang Liu, Xingpeng Zhang +7Diffusion Sampling Diffusion-Based Planning
Data Science & Artificial Intelligence Research Institute, China Unicom · Unicom Data Intelligence, China Unicom · School of Computer Science and Software Engineering, Southwest Petroleum University +2
Fractals made Practical: Denoising Diffusion as Partitioned Iterated Function Systems
Mar 13, 2026Ann DoomsDiffusion-Based Denoising Diffusion Models
Department of Mathematics & Data Science Vrije Universiteit Brussel Pleinlaan 2, 1050 Brussels, BELGIUM
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
Mar 10, 2026Junyi An, Chao Qu, Yun-Fei Shi +33D Molecular Generation Molecular Generation
Shanghai Academy of Artificial Intelligence for Science, SAIS · Artificial Intelligence Innovation and Incubation (AI3) Institute, Fudan University
Sparse Scheduled Diffusion Guidance for Inverse Problems
Mar 9, 2026Abduragim Shtanchaev, Albina Ilina, Yazid Janati +3Diffusion-Based Inverse Problems Diffusion Posterior Sampling
MBZUAI, Abu Dhabi, United Arab Emirates · Institute of Foundation Models · EPITA, Paris, France
AdaGen: Learning Adaptive Policy for Image Synthesis
Mar 7, 2026Zanlin Ni, Yulin Wang, Yeguo Hua +5Diffusion Timestep Scheduling RL for Image Generation
Department of Automation, BNRist, Tsinghua University, Beijing, China. · Taobao & Tmall Group of Alibaba.
Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers
Mar 5, 2026Guandong LiDiffusion Model Caching Diffusion Model Inference Acceleration
iFLYTEK
Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models
Feb 28, 2026Zhenyu Zhou, Defang Chen, Siwei Lyu +2Diffusion Model Inference Acceleration T2I Diffusion Models
State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · University of California, Berkeley +1
Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness
Feb 28, 2026Yuyang Chen, Linqian Zeng, Yijin ZHou +2Diffusion Timestep Scheduling Diffusion Model Inference Acceleration
Shanghai Jiaotong University · Tsinghua University
Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache
Feb 26, 2026Bowen Cui, Yuanbin Wang, Huajiang Xu +6Diffusion Model Inference Acceleration Diffusion Model Caching
Alibaba Group
Variational Trajectory Optimization of Anisotropic Diffusion Schedules
Feb 23, 2026Pengxi Liu, Zeyu Michael Li, Xiang ChengDiffusion Models Diffusion Timestep Scheduling
Department of Electrical and Computer Engineering, Duke University
Noise Scheduling as Information-Guided Allocation in Diffusion Training
Feb 20, 2026Gabriel Raya, Bac Nguyen, Georgios Batzolis +6Diffusion Timestep Scheduling
Tilburg University & JADS · Sony AI · University of Cambridge +2

Jun 13, 2026J/K move · Enter open · S save

Timestep Rescheduling in Diffusion Inversion

Shangquan Sun, Ting Gong, Zhirui Liu, Jiamin Wu+4

School of CyberScience and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen 518107, China · Tsinghua University · CUHK+2

Diffusion Model Inversion Diffusion Sampling Diffusion Timestep Scheduling Diffusion-Based Image Editing

Open paper AskPDF arXiv

Diffusion inversion, which maps images back to the Gaussian latent space of a diffusion model, is a critical task for image reconstruction and editing. While DDIM enables fast deterministic inversion, it inherently introduces deviations that accumulate into noticeable inversion errors. Existing methods often address this by solving a fixed-point problem but largely overlook how the selection of the diffusion timestep in the noise scheduler influences inversion fidelity. In this work, we reveal that the deviation scale in diffusion inversion is strongly dependent on the timestep size, and exhibits a parabolic trend, with larger errors concentrated at both small and large timesteps. Based on this finding, we propose a simple yet effective nonuniform timestep scheduler that integrates a global rescaling with a local dynamic programming based rescheduling, enabling a strategic allocation of computational effort that minimizes the overall inversion error and preserves higher inversion accuracy. Our method serves as an off-the-shelf enhancement for existing inversion techniques and requires no extra parameters or computational overhead. Through extensive experiments, we verify that integrating our scheduler consistently boosts the performance of existing inversion methods, achieving superior results in image reconstruction and editing.